Pinned
We've been building Qoder with Qoder for 9 months. 60+ releases, one every 4 days.
Today we hit 1.0.
From AI IDE to Autonomous Development Desktop.
You define. They ship.
00:00
Qoder
491 posts
Qoder
@qoder_ai_ide
Agentic Coding Platform for Real Software. Think deeper, build better.
- Off-Peak Rates are live across all Qoder products. Qwen 3.7 Max: 80% off. Qwen 3.7 Plus: 60% off. 10 hours every day. Automatic. No opt-in needed. If you're in the Americas, here's the twist: off-peak covers most of your workday. 🧵
Replying to @qoder_ai_ideHow to use: 1. Open any Qoder product (Desktop, CLI, QoderWork, QoderWake, Cloud Agents, JetBrains) 2. Switch to Qwen3.7-Max or Qwen3.7-Plus in model selector That's it. Discount applies automatically during off-peak window. Set timed tasks, let them execute during off-peak. OrIt's structural pricing, no end date announced yet. Big refactors, Experts mode, /schedule, /goal, /loop, batch jobs...the tasks you've been rationing credits on. Time to let them run. Off-Peak Rates details 👇 - Qoder now ships GLM-5.2 — Purpose-built for long-horizon tasks. - Solid 1M context, actually usable - Open-source SOTA on Code Arena - Solves the hardest part of agentic engineering: Long Horizon Tasks To enable: Model selector → GLM-5.2 qoder.com
- The Qwen3.7-Max promotion — 200 free daily calls and 50% off pricing — will end on June 22, 2026 at 23:59:59 (SGT). Try it before it's gone, and stay tuned for our upcoming promotion.🔥Qwen3.7-Max, halved. Starting today, Qwen3.7-Max — the latest flagship from the @Alibaba_Qwen family — is half price on Qoder. Limited time. New here? You also get 100 free model calls a day. Auto-applied. No claim. No toggle. Desktop, JetBrains Plugin, CLI, QoderWork,
- QoderWork can now remember things across sessions, reflect on what matters, and turn repeated tasks into reusable skills. - Memory: stored as local Markdown files. You see, edit, and delete everything. - Reflection: after sessions, the AI curates memories (promotes, corrects,
- Qoder now ships with Kimi K2.7 Code — purpose-built for long-context coding. Precise instruction following. Reliable long-horizon execution. 30% fewer tokens wasted on overthinking. Live now across Desktop, JetBrains, CLI & QoderWake — Fast mode for 6x speed starts Monday.
Replying to @qoder_ai_ideThis directly translates to better Agentic performance in Qoder. When your Agent runs a multi-file refactor or a full feature implementation, the underlying reasoning is now tighter, faster, and more decisive. - Ultimate half price ends tonight (June 12, 00:00 SGT). If you're looking for what's next: Qwen 3.7 Max has two deals running right now 👇 → Half price: docs.qoder.com/events/qwen-ma… → 200 free calls/day: docs.qoder.com/events/qwen-ma…Ultimate, halved. Starting today, the Ultimate tier on Qoder is half price, drops from 1.6x to 0.8x. Limited time. Auto-applied. No claim. No toggle. Pro / Pro+ / Ultra. IDE, JetBrains, CLI. Now's a good time to put it on something hard. 🤝
- Qoder Desktop v1.6.0 is out. Quest now supports remote control. Install Qoder Mobile or add the web app to your phone screen, sign in with the same account. Your running Quests show up on your phone. Review progress, respond to questions, approve changes. Kick off a task, and
00:00Replying to @qoder_ai_ideBuilt-in Experts now support custom system prompts. Shape how each expert behaves to match your codebase and conventions. Custom sub-agents can pick their own model too. Strong model on your code reviewer, fast model on your formatter. You decide what runs where.Also more enhancements in v1.6.0: - Wider drag-drop zone in Quest (files land where you expect now) - Better knowledge retrieval relevance - Faster local indexing, less sync lag 👇 - Qoder v1.5.2: Knowledge engine big update. Repo Wiki (for you) and Knowledge Cards (for agents) are now generated together from your codebase. Combined with Memory, all three feed into one unified engine. Context retrieval accuracy: 40% to 77% across 92 real-world test cases.
00:00What's new: - /knowledge: built-in agent to read or edit project knowledge right in chat - Voice input auto-polishes transcription - Large repo perf improvements for wiki and card generation - Smarter knowledge retrieval on code changes - Quest mode UX improvements
00:00Pairs well with Qwen3.7-Max. Strong reasoning + project delivery, and it's still free (200 calls/day). Knowledge Center gives the coding agent the right project context. Qwen3.7-Max gives it the muscle. Try the combo. Upgrade to v1.5.2 and enjoy. 👉🏻
